pico-decoder-large / config.json
rdiehlmartinez's picture
pico-decoder-large-1 trained to 50k steps
6bfde12
{
"activation_hidden_dim": 6144,
"architectures": [
"PicoHF"
],
"attention_n_heads": 12,
"attention_n_kv_heads": 4,
"auto_map": {
"AutoConfig": "pico.PicoHFConfig",
"AutoModelForCausalLM": "pico.PicoHF"
},
"batch_size": 1024,
"d_model": 1536,
"max_seq_len": 2048,
"model_type": "pico",
"n_layers": 12,
"norm_eps": 1e-06,
"position_emb_theta": 10000.0,
"torch_dtype": "float32",
"transformers_version": "4.48.1",
"vocab_size": 50304
}